Active Object Tracking (AOT) aims to maintain a specific relation between the tracker and object(s) by autonomously controlling the motion system of a tracker given observations. AOT has wide-ranging applications, such as in mobile robots and autonomous driving. However, building a generalizable active tracker that works robustly across different scenarios remains a challenge, especially in unstructured environments with cluttered obstacles and diverse layouts. We argue that constructing a state representation capable of modeling the geometry structure of the surroundings and the dynamics of the target is crucial for achieving this goal. To address this challenge, we present RSPT, a framework that forms a structure-aware motion representation by Reconstructing the Surroundings and Predicting the target Trajectory. Additionally, we enhance the generalization of the policy network by training in an asymmetric dueling mechanism. We evaluate RSPT on various simulated scenarios and show that it outperforms existing methods in unseen environments, particularly those with complex obstacles and layouts. We also demonstrate the successful transfer of RSPT to real-world settings. Project Website: https://sites.google.com/view/aot-rspt.

翻译：主动目标跟踪（Active Object Tracking，AOT）旨在通过自主控制追踪器的运动系统，在观测条件下维持追踪器与目标之间的特定关系。该技术广泛应用于移动机器人和自动驾驶等领域。然而，构建一个跨场景鲁棒工作的可泛化主动追踪器仍面临挑战，尤其是在存在杂乱障碍物和多样化布局的非结构化环境中。本文认为，构建能够建模周围环境几何结构与目标运动状态的状态表征是实现该目标的关键。为此，我们提出RSPT框架，通过重建环境结构（Reconstructing the Surroundings）与预测目标轨迹（Predicting the Target Trajectory）形成结构感知的运动表征。此外，我们采用非对称对抗机制训练策略网络以增强其泛化能力。在多个仿真场景中的评估表明，RSPT在未知环境（尤其具有复杂障碍物和布局的场景）中优于现有方法，并成功实现了向真实世界的迁移。项目网站：https://sites.google.com/view/aot-rspt。